diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c index 07381410ad5..5c9170e3a1d 100644 --- a/gcc/config/i386/i386-expand.c +++ b/gcc/config/i386/i386-expand.c @@ -93,9 +93,6 @@ along with GCC; see the file COPYING3. If not see #include "i386-builtins.h" #include "i386-expand.h" -static bool ix86_expand_vector_init_duplicate (bool, machine_mode, rtx, - rtx); - /* Split one or more double-mode RTL references into pairs of half-mode references. The RTL can be REG, offsettable MEM, integer constant, or CONST_DOUBLE. "operands" is a pointer to an array of double-mode RTLs to @@ -13909,7 +13906,7 @@ static bool expand_vec_perm_1 (struct expand_vec_perm_d *d); /* A subroutine of ix86_expand_vector_init. Store into TARGET a vector with all elements equal to VAR. Return true if successful. */ -static bool +bool ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, rtx target, rtx val) { diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h index 71745b9a1ea..51376fcc454 100644 --- a/gcc/config/i386/i386-protos.h +++ b/gcc/config/i386/i386-protos.h @@ -258,6 +258,8 @@ extern void ix86_expand_mul_widen_hilo (rtx, rtx, rtx, bool, bool); extern void ix86_expand_sse2_mulv4si3 (rtx, rtx, rtx); extern void ix86_expand_sse2_mulvxdi3 (rtx, rtx, rtx); extern void ix86_expand_sse2_abs (rtx, rtx); +extern bool ix86_expand_vector_init_duplicate (bool, machine_mode, rtx, + rtx); /* In i386-c.c */ extern void ix86_target_macros (void); diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index d3f5a74f763..f0b450ab4be 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -24814,3 +24814,34 @@ "TARGET_WIDEKL" "aes\t{%0}" [(set_attr "type" "other")]) + +;; Modes handled by broadcast patterns. NB: Allow V64QI and V32HI with +;; TARGET_AVX512F since ix86_expand_vector_init_duplicate can expand +;; without TARGET_AVX512BW which is used by memset vector broadcast +;; expander to XI with: +;; vmovd %edi, %xmm15 +;; vpbroadcastb %xmm15, %ymm15 +;; vinserti64x4 $0x1, %ymm15, %zmm15, %zmm15 + +(define_mode_iterator INT_BROADCAST_MODE + [(V64QI "TARGET_AVX512F") (V32QI "TARGET_AVX") V16QI + (V32HI "TARGET_AVX512F") (V16HI "TARGET_AVX") V8HI + (V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX") V4SI + (V8DI "TARGET_AVX512F && TARGET_64BIT") + (V4DI "TARGET_AVX && TARGET_64BIT") (V2DI "TARGET_64BIT")]) + +;; Broadcast from an integer. NB: Enable broadcast only if we can move +;; from GPR to SSE register directly. +(define_expand "vec_duplicate" + [(set (match_operand:INT_BROADCAST_MODE 0 "register_operand") + (vec_duplicate:INT_BROADCAST_MODE + (match_operand: 1 "nonimmediate_operand")))] + "TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC" +{ + if (!ix86_expand_vector_init_duplicate (false, + GET_MODE (operands[0]), + operands[0], + operands[1])) + gcc_unreachable (); + DONE; +})